Agent Skills

Create and run any AI agents systems from 6k+ tools. Give your AI hands access to your Android.

Install

npx cmdssi mcp https://api.melaya.org/mcp
README

Melaya MCP Server

Let an AI assistant use your Android phone, your browser, and the rest of your Melaya account.

Also listed on mcp.so · mcpserver.dev · mcpmarket · cursor.directory · Glama · Product Hunt · AlternativeTo · SaaSHub · AI Agents Directory · AgentLocker · LaunchKiwi

Documentation · Melaya · Device Control · MCP Server

Melaya pairs a phone to your account and gives an agent the same view of it a person has: it reads the screen through Android's accessibility tree, then taps, types, swipes, and moves between apps. No per-app integration, no vendor API. If you can use the app, so can the agent.

This is a remote Model Context Protocol server. MCP is a vendor-neutral standard, so one endpoint works everywhere:

https://api.melaya.org/mcp

Nothing to install, no SDK required.

Connect


Claude Code
claude mcp add --transport http melaya https://api.melaya.org/mcp

Codex CLI
codex mcp add melaya --url https://api.melaya.org/mcp

Direct HTTP needs experimental_use_rmcp_client = true in ~/.codex/config.toml.


Cursor

~/.cursor/mcp.json, or .cursor/mcp.json for one project:

{ "mcpServers": { "melaya": { "url": "https://api.melaya.org/mcp" } } }

Claude

claude.ai, Desktop and mobile: Settings → Connectors → Add custom connector, paste https://api.melaya.org/mcp


ChatGPT

Settings → Connectors → Developer mode, paste the same endpoint


Le Chat

Connectors → Add custom MCP connector

VS Code
code --add-mcp '{"name":"melaya","type":"http","url":"https://api.melaya.org/mcp"}'
Everything else

Windsurf, Zed, Cline, Goose, Lovable, Gemini CLI, Qwen Code and any other MCP client take the same block, in whichever file that client uses for MCP servers:

{ "mcpServers": { "melaya": { "url": "https://api.melaya.org/mcp" } } }

Authentication is OAuth 2.1 with PKCE. You choose which permissions to grant on a Melaya consent page; the assistant receives a scoped token. Your password is never shared.

Then just ask:

Connect my phone and go through my unread Instagram DMs.


Give your AI the Melaya skill

This server gives your assistant the tools. The Melaya skill gives it the method: which tool to call first, how to connect services, build and validate a pipeline on a real run, set triggers and approvals, and read results. Install both and your assistant gets real work right the first time instead of guessing.

Any assistant (ChatGPT, Gemini, Cursor, …): paste this line.

Install the Melaya skill from https://github.com/melaya-labs/melaya/tree/main/skills/melaya and use it whenever I ask you to work with Melaya.

Claude Code: copy it into your skills folder, then restart. It loads on its own when you mention Melaya.

git clone --depth 1 https://github.com/melaya-labs/melaya /tmp/melaya && cp -r /tmp/melaya/skills/melaya ~/.claude/skills/

Claude.ai and Claude Desktop: download skills/melaya as a .zip and upload it under Settings → Capabilities → Skills. Anywhere else, add SKILL.md as a project instruction or rules file.

Starts right
Opens every session with melaya_setup_status and closes each gap it reports before doing anything else.
Stays safe
Never asks for a key in chat, never decides an approval for you, confirms before anything is sent or deleted.
Builds pipelines that run
Reads the config before changing it, previews before saving, and judges a run by its real output, not its status.
Loads only what it needs
One short router plus eleven modules: quickstart, pipelines, agentic systems, data, triggers and approvals, devices, handover.

What it can do

Operate your phone

Read the screen, open apps, tap, type, scroll, swipe, screenshot. You watch it work, and one control stops everything.

Melaya ships navigation playbooks for common apps, so the agent arrives knowing where things are instead of exploring blindly.

Operate a browser

The same read-act-verify loop on a desktop site, through the Melaya extension on Chrome or Edge. You attach the tab; the model never picks one.

It can also debug the page it is on: network activity, console output, and a performance diagnosis that ranks causes with the file and the number behind each, rather than handing over a raw panel. Credential values are redacted at capture, before anything reaches the model.

Build and run agents

Create a project for the work (one per client pilot, say), list the template library and instantiate a validated template, or author a pipeline from scratch, validate it before saving, schedule it, and watch it run. Hand a long or recurring job to an autonomous agent on your own machine, on your own model subscription, that carries on after the conversation ends.

Read, and act through, your connected services

Mail, documents, your ERP. Read-only by default, structurally: without the separate write permission the write path is blocked in two independent places, so a write stays blocked even if Melaya's own tool catalog is out of date.

Grant melaya:connectors.write as well and the assistant can act for you there too: send an email, create or update a record or a file. Anything that moves money or trades is excluded at every permission level: payments, refunds, purchases, transfers, ad-spend changes and orders are refused by the server, and again by the executor, and stay with you in the Melaya app. Every write made this way is audit-logged.

Manage projects

Create a project, rename it or edit its description, and delete it once it is empty. Delete is a dry run until confirmed, only the project's creator can do it, and a project that still holds pipelines, run history or other members is refused. Plan limits apply exactly as in the app.

Find out what happened

Runs, transcripts, tool traces, failure diagnosis, cost, and what your agents have learned across runs.


What it cannot do

Enforced on the device itself, not on the server, so no prompt and no agent instruction can move them.

It only touches what you allow-list

Apps on the phone, origins in the browser. The agent can hand access back, narrowing the list or clearing it, but only you can grant it.

That asymmetry is deliberate. The agent reads text off your screen, and text can be written by anyone: a message, a comment, a web page. A boundary it could widen in response to what it reads would not be a boundary.

Publishing and paying always ask you

You see the exact text before it goes out, and approvals reach you even when the phone is locked.

 

There is a STOP control

On the phone overlay and in the Melaya app. It halts everything immediately, across every agent and every connected assistant.

Approvals are listed here, never decided here

The gate exists to put a human between an agent and a consequential action, and the caller here is a model reading untrusted content. You approve in the Melaya app or on your phone.

Password fields are excluded from screen reads.

Also deliberately absent, and enforced by tests rather than by convention: trading and moving money through a connector (they write against live exchange keys and payment accounts), administration (no honest consent sentence exists for it), and credential values of any kind.


Permissions

Ten scopes. You grant them individually.

ScopeWhat it allows
melaya:readYour workspace: pipelines, runs, traces, evaluations, pending approvals
melaya:platformYour account and plan: tier, usage against limits, subscription
melaya:runnerSet up and check the Melaya runner on your computer
melaya:phoneOperate your paired Android phone, inside apps you allow-listed
melaya:browserOperate a connected browser, on sites you allowed
melaya:pipelinesCreate, edit, schedule, run and cancel agent pipelines
melaya:projectsCreate projects, rename them and edit descriptions, delete an empty project you created
melaya:connectorsRead data from connected services. Read only
melaya:connectors.writeAct through connected services: send emails, create or update records and files. Needs melaya:connectors. Never moves money or trades
melaya:teamRead project membership, and invite people you name

The tool list your assistant receives is filtered to what you granted, so connecting for phone control alone shows 23 tools rather than all 88. If a capability seems missing, you declined it; reconnect and approve it.

[!NOTE] If you also use the Melaya SDK, "connectors" means something different there. In the SDK it is project credential storage. Here, melaya:connectors is reading data from services you already connected, and melaya:connectors.write is acting through them. This surface cannot store, read or delete a credential.

Requirements

  • A Melaya account — free at melaya.org
  • An Android phone (Android 8 or newer) for phone control. There is no iOS build.
  • The Melaya extension on Chrome or Edge for browser control
  • For autonomous agents: Node 18+, Python 3.11+, and a signed-in CLI on the machine hosting the runner

Privacy

Screen and page content read during a run goes to Melaya and to whichever model you selected, for the duration of that run. The privacy policy covers collection, retention and deletion.

One credential does cross the boundary, and it is worth naming: if you set up the optional local runner, the command you are given contains a runner token. It is valid for 7 days, revocable in settings or with melaya_runner_revoke, and unavoidable because the runner starts from a command line. On a hosted assistant that command appears in your conversation history. Nothing else does; provider and connector credentials are resolved server-side and never reach the assistant.

Disconnecting in Melaya settings immediately revokes the connection's ability to renew itself. A token it already holds keeps working until it expires, at most one hour.

What's in this repo

PathPurpose
server.jsonManifest for the official MCP Registry
.mcp.jsonRemote server declaration
.claude-plugin/, skills/, commands/Claude Code plugin packaging — one distribution of the same server

The server itself runs as part of the Melaya platform; this repo is its public manifest, packaging and documentation.

The rest of the platform

This server is one surface onto Melaya. Its tool domains map to the products behind them, so if a scope is useful the product page explains what it reaches:

ProductWhat it ismelaya: scope
Melaya AgentsVisual builder for agent pipelines, 6,912 tools and 103 subagentspipelines
Melaya AssistantThe governed operating layer over those agentsplatform
Device ControlAndroid phone control through the accessibility treephone
Melaya Browser ControlOrigin-scoped control of a paired browserbrowser
Melaya MarketingAds, search consoles, analytics, DNS and site in one cockpit, with approval before anything touches real money or your live siteconnectors
Melaya MCP ServerThis serverall of the above

The browser extension is what Browser Control talks to, and ships for Chrome, Edge, Brave, Opera and Firefox.

Pricing starts at a $0 Sandbox tier for evaluating the platform during open beta: see plans.

Links


Melaya Labs · melaya.org · Discord

License

Apache-2.0, matching the Melaya SDKs.

It covers what is in this repository — the registry manifest, the plugin packaging, the skills and this documentation. It is not a licence to the Melaya service itself: using the hosted server at api.melaya.org needs a Melaya account and is governed by the Terms.

Search skills and MCP servers

Search across 31,816 skills and MCPs